create_media_upload

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations limited to hints, the description carries the burden and delivers: it reveals the two-phase behavior (slot creation only, no byte upload), the auth-omission requirement for the PUT, the ordering dependency on generate_motion_from_video, the 30-second/250 MB constraints, and a security caution to keep signed URLs private. None of this contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences with the primary purpose front-loaded, followed by scope clarification, workflow, and grouped constraints. No filler; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-phase tool with no output schema, the description names the key returned field (mediaUploadURL) and lays out the full lifecycle. It does not mention slot expiry, behavior on repeated calls, or error cases, but an agent has what it needs to invoke and follow through correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the prose must compensate. It adds the 250 MB limit that the schema cannot express and frames the media array as 'selected local videos,' clarifying the intent behind name/extension. It does not explicitly explain every field (e.g., resolution format), but the schema's enum, pattern, and maximum make those partially self-documenting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence 'Prepare signed upload URLs for video references' gives a specific verb and resource, and the second sentence disambiguates from actual byte upload ('it does not upload the file bytes'). It also distinguishes the tool from the sibling generate_motion_from_video by positioning this step before it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit workflow instructions: use the client's authorized file tools to PUT each video to the returned mediaUploadURL without an API key header, and upload before calling generate_motion_from_video. It provides clear context but does not name a competing alternative tool or state when not to use this one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.